Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2402 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6438. Min Range: -5.6438
Max Act: 5.6438. Min Act: -0.1700
Data Index: 1128467 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6438. Min Range: -5.6438
Max Act: 5.5188. Min Act: -0.1700
Data Index: 8492176 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6438. Min Range: -5.6438
Max Act: 5.3625. Min Act: -0.1700
Data Index: 4314626 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6438. Min Range: -5.6438
Max Act: 5.3625. Min Act: -0.1700
Data Index: 6669587 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6438. Min Range: -5.6438
Max Act: 5.3625. Min Act: -0.1700
Data Index: 3100278 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6438. Min Range: -5.6438
Max Act: 5.3000. Min Act: -0.1700
Data Index: 1354462 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6438. Min Range: -5.6438
Max Act: 5.2688. Min Act: -0.1700
Data Index: 2707153 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6438. Min Range: -5.6438
Max Act: 5.3000. Min Act: -0.1700
Data Index: 6291385 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6438. Min Range: -5.6438
Max Act: 5.2375. Min Act: -0.1700
Data Index: 2549258 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6438. Min Range: -5.6438
Max Act: 5.2688. Min Act: -0.1700
Data Index: 5529541 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6438. Min Range: -5.6438
Max Act: 5.2375. Min Act: -0.1700
Data Index: 7260471 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6438. Min Range: -5.6438
Max Act: 5.2063. Min Act: -0.1700
Data Index: 4443728 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6438. Min Range: -5.6438
Max Act: 5.2063. Min Act: -0.1700
Data Index: 1173505 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6438. Min Range: -5.6438
Max Act: 5.2063. Min Act: -0.1700
Data Index: 8205379 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6438. Min Range: -5.6438
Max Act: 5.1750. Min Act: -0.1700
Data Index: 6750544 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6438. Min Range: -5.6438
Max Act: 5.1750. Min Act: -0.1700
Data Index: 70937 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6438. Min Range: -5.6438
Max Act: 5.1438. Min Act: -0.1700
Data Index: 2453484 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6438. Min Range: -5.6438
Max Act: 5.1125. Min Act: -0.1700
Data Index: 2784085 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6438. Min Range: -5.6438
Max Act: 5.1438. Min Act: -0.1700
Data Index: 2004697 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6438. Min Range: -5.6438
Max Act: 5.1438. Min Act: -0.1700
Data Index: 6634077 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #19